Skip to content
Qwen

Qwen3 Coder 30B A3B Instruct

Qwen3 Coder 30B A3B Instruct is a large language model made by Qwen, added to the catalog on 31 Jul 2025. It has a context window of 262,144 tokens and costs $0.07 per 1M input tokens and $0.28 per 1M output tokens. It accepts text and produces text. Typical uses: generate complex code structures efficiently, understand and process repository-scale data and perform structured code completion tasks.

Price checked ยท source: OpenRouter

What Qwen3 Coder 30B A3B Instruct is

Discover the Qwen3 Coder 30B A3B Instruct, a versatile AI model developed by Qwen, released in July 2025. This model boasts a 30.5 billion parameter Mixture-of-Experts architecture with 128 experts, making it well-suited for complex code generation and repository-scale understanding. With a native context length of 256K tokens, extendable up to 1 million with Yarn, it excels in tasks like function calls and structured code completion. Designed for instruction-following, it integrates seamlessly with OpenAI-compatible tools, ensuring efficient text-to-text processing.

Key features

  • 30.5B parameter Mixture-of-Experts model
  • Native 256K tokens context, extendable to 1M
  • Optimized for instruction-following tasks
  • Seamless OpenAI-compatible tool integration
  • Supports advanced code generation and understanding

Typical uses

  • Generate complex code structures efficiently
  • Understand and process repository-scale data
  • Perform structured code completion tasks
  • Execute function calls with precision
  • Integrate with existing OpenAI-compatible tools

Qwen3 Coder 30B A3B Instruct pricing

US dollars, list price through OpenRouter.

Checked
Qwen3 Coder 30B A3B Instruct price list
ItemStandard
Input, per 1M tokens$0.07
Output, per 1M tokens$0.28

The price last changed on 21 Nov 2026. One price change has been recorded since Qwen3 Coder 30B A3B Instruct was added.

Qwen3 Coder 30B A3B Instruct price history, newest first, in US dollars per 1M tokens
DateInput /1MOutput /1M
$0.07$0.28
$0.15$0.60
What typical tasks cost with Qwen3 Coder 30B A3B Instruct
What a task costsCost
Answer a short question500 in / 300 out$0.0001
Summarise a 50-page PDF25,000 in / 800 out$0.0020
Review a 2,000-line source file30,000 in / 2,000 out$0.0027
Read a 300-page contract set150,000 in / 1,500 out$0.011
Check the provider's pageToken counts are estimates. A maker's direct price and its monthly plans can differ from the per-token price shown here.

Qwen3 Coder 30B A3B Instruct specifications

Qwen3 Coder 30B A3B Instruct limits and identity
Model idqwen/qwen3-coder-30b-a3b-instruct
Versionqwen3-coder-30b-a3b-instruct
Context window262,144 tokensAbout 196,608 English words
Max output235,929 tokens
Knowledge cutoff2025-06-30
Added to catalog31 Jul 2025
Qwen3 Coder 30B A3B Instruct capabilities
Input typestext
Output typestext
Tool callingYes
Structured outputsYes
Reasoning effort controlNo
Content moderationNot applied by provider

Sample outputs

The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.

Write a short essay

RUN20 Nov 2026
Prompt

Write 150 words on how AI might positively upend work, leisure and creativity

Output

AI has the potential to revolutionize work, leisure, and creativity by automating routine tasks and amplifying human capabilities. In work, AI can handle repetitive processes like data entry, scheduling, and basic analysis, freeing professionals to focus on strategic thinking, problem-solving, and interpersonal communication. This shift could lead to more fulfilling careers and reduced burnout. For leisure, AI-powered personalization will create hyper-targeted entertainment experiences, from customized movie recommendations to intelligent fitness programs that adapt to individual preferences and progress. Smart assistants could manage household tasks, allowing more time for hobbies and relationships. In creativity, AI serves as a collaborative partner rather than replacement. Writers can brainstorm ideas, artists can explore new styles, and musicians can experiment with novel compositions. AI tools democratize creative expression, making professional-grade resources accessible to everyone while enhancing human imagination rather than replacing it.

Qwen3 Coder 30B A3B Instruct questions

How much does Qwen3 Coder 30B A3B Instruct cost?

Qwen3 Coder 30B A3B Instruct costs $0.07 per 1M input tokens and $0.28 per 1M output tokens through OpenRouter, as checked on 22 Nov 2026. Summarising a 50-page PDF costs about $0.0020.

What is the context window of Qwen3 Coder 30B A3B Instruct?

262,144 tokens, or roughly 196,608 English words. It can write up to 235,929 tokens in one response.

Can Qwen3 Coder 30B A3B Instruct read images and PDFs?

No. It accepts text only. It produces text, so it cannot generate images.

How do I try Qwen3 Coder 30B A3B Instruct?

Use the "Try Qwen3 Coder 30B A3B Instruct" button on this page. It opens the chat with Qwen3 Coder 30B A3B Instruct selected; you type the question and press send.

Try Qwen3 Coder 30B A3B Instruct on your own question.

It opens in the chat with this model already selected.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.